{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:J2SVTPZP3R7T5VJVRG4XHTZGR5","short_pith_number":"pith:J2SVTPZP","canonical_record":{"source":{"id":"2412.14637","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-12-19T08:48:29Z","cross_cats_sorted":[],"title_canon_sha256":"40f250f2a47981d0dd37fdbae61322d0c49221ac25dba7e4f28263d45905d718","abstract_canon_sha256":"ddf2d423b55f8ecb2f20fea4d7b4654fa61f00415d741f88a0a5cbff35e6e3f0"},"schema_version":"1.0"},"canonical_sha256":"4ea559bf2fdc7f3ed53589b973cf268f58641fb89ffc03fb1c83c432429e6641","source":{"kind":"arxiv","id":"2412.14637","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14637","created_at":"2026-07-05T09:51:50Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14637v1","created_at":"2026-07-05T09:51:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14637","created_at":"2026-07-05T09:51:50Z"},{"alias_kind":"pith_short_12","alias_value":"J2SVTPZP3R7T","created_at":"2026-07-05T09:51:50Z"},{"alias_kind":"pith_short_16","alias_value":"J2SVTPZP3R7T5VJV","created_at":"2026-07-05T09:51:50Z"},{"alias_kind":"pith_short_8","alias_value":"J2SVTPZP","created_at":"2026-07-05T09:51:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:J2SVTPZP3R7T5VJVRG4XHTZGR5","target":"record","payload":{"canonical_record":{"source":{"id":"2412.14637","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-12-19T08:48:29Z","cross_cats_sorted":[],"title_canon_sha256":"40f250f2a47981d0dd37fdbae61322d0c49221ac25dba7e4f28263d45905d718","abstract_canon_sha256":"ddf2d423b55f8ecb2f20fea4d7b4654fa61f00415d741f88a0a5cbff35e6e3f0"},"schema_version":"1.0"},"canonical_sha256":"4ea559bf2fdc7f3ed53589b973cf268f58641fb89ffc03fb1c83c432429e6641","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:50.614055Z","signature_b64":"gTMLeeirKrolD3BmxCP09qsPLu+iZux5HSYLkwMmmAncIxmihx5s1lJP8DJUQpexuq5fyQxkwLhgtZP63/SuBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ea559bf2fdc7f3ed53589b973cf268f58641fb89ffc03fb1c83c432429e6641","last_reissued_at":"2026-07-05T09:51:50.613533Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:50.613533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.14637","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:51:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gS20Nk8OlhCNPJ1QPVN6cUgSLpmErQuuLyOO1fjEsphirIprERw2EQ1RNhMNn6IZKpMolvwwTFnYApdWY773Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T00:02:39.795575Z"},"content_sha256":"5f6ccdb8172dab4bbcad862b038020a4f21fc5485eb17cfcb1ac29b337f84310","schema_version":"1.0","event_id":"sha256:5f6ccdb8172dab4bbcad862b038020a4f21fc5485eb17cfcb1ac29b337f84310"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:J2SVTPZP3R7T5VJVRG4XHTZGR5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Complexities of Armijo-like algorithms in Deep Learning context","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Bensaid Bilel (IMB)","submitted_at":"2024-12-19T08:48:29Z","abstract_excerpt":"The classical Armijo backtracking algorithm achieves the optimal complexity for smooth functions like gradient descent but without any hyperparameter tuning. However, the smoothness assumption is not suitable for Deep Learning optimization. In this work, we show that some variants of the Armijo optimizer achieves acceleration and optimal complexities under assumptions more suited for Deep Learning: the (L 0 , L 1 ) smoothness condition and analyticity. New dependences on the smoothness constants and the initial gap are established. The results theoretically highlight the powerful efficiency of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14637","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.14637/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:51:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ahd2k7mZONVu2UdDpfauNm1kR57x4HxAXwRMWEoe4UyZ5o3HXraYVL10k9PqbXO0V0Fy5SX0uCzTo5PWo6pFDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T00:02:39.796100Z"},"content_sha256":"5d0432cecb3e0b0d110a153c9f16206ae244565911fa6e866f6fd0d07d3e0af1","schema_version":"1.0","event_id":"sha256:5d0432cecb3e0b0d110a153c9f16206ae244565911fa6e866f6fd0d07d3e0af1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J2SVTPZP3R7T5VJVRG4XHTZGR5/bundle.json","state_url":"https://pith.science/pith/J2SVTPZP3R7T5VJVRG4XHTZGR5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J2SVTPZP3R7T5VJVRG4XHTZGR5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-23T00:02:39Z","links":{"resolver":"https://pith.science/pith/J2SVTPZP3R7T5VJVRG4XHTZGR5","bundle":"https://pith.science/pith/J2SVTPZP3R7T5VJVRG4XHTZGR5/bundle.json","state":"https://pith.science/pith/J2SVTPZP3R7T5VJVRG4XHTZGR5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J2SVTPZP3R7T5VJVRG4XHTZGR5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:J2SVTPZP3R7T5VJVRG4XHTZGR5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ddf2d423b55f8ecb2f20fea4d7b4654fa61f00415d741f88a0a5cbff35e6e3f0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-12-19T08:48:29Z","title_canon_sha256":"40f250f2a47981d0dd37fdbae61322d0c49221ac25dba7e4f28263d45905d718"},"schema_version":"1.0","source":{"id":"2412.14637","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14637","created_at":"2026-07-05T09:51:50Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14637v1","created_at":"2026-07-05T09:51:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14637","created_at":"2026-07-05T09:51:50Z"},{"alias_kind":"pith_short_12","alias_value":"J2SVTPZP3R7T","created_at":"2026-07-05T09:51:50Z"},{"alias_kind":"pith_short_16","alias_value":"J2SVTPZP3R7T5VJV","created_at":"2026-07-05T09:51:50Z"},{"alias_kind":"pith_short_8","alias_value":"J2SVTPZP","created_at":"2026-07-05T09:51:50Z"}],"graph_snapshots":[{"event_id":"sha256:5d0432cecb3e0b0d110a153c9f16206ae244565911fa6e866f6fd0d07d3e0af1","target":"graph","created_at":"2026-07-05T09:51:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.14637/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The classical Armijo backtracking algorithm achieves the optimal complexity for smooth functions like gradient descent but without any hyperparameter tuning. However, the smoothness assumption is not suitable for Deep Learning optimization. In this work, we show that some variants of the Armijo optimizer achieves acceleration and optimal complexities under assumptions more suited for Deep Learning: the (L 0 , L 1 ) smoothness condition and analyticity. New dependences on the smoothness constants and the initial gap are established. The results theoretically highlight the powerful efficiency of","authors_text":"Bensaid Bilel (IMB)","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-12-19T08:48:29Z","title":"Complexities of Armijo-like algorithms in Deep Learning context"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14637","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5f6ccdb8172dab4bbcad862b038020a4f21fc5485eb17cfcb1ac29b337f84310","target":"record","created_at":"2026-07-05T09:51:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ddf2d423b55f8ecb2f20fea4d7b4654fa61f00415d741f88a0a5cbff35e6e3f0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-12-19T08:48:29Z","title_canon_sha256":"40f250f2a47981d0dd37fdbae61322d0c49221ac25dba7e4f28263d45905d718"},"schema_version":"1.0","source":{"id":"2412.14637","kind":"arxiv","version":1}},"canonical_sha256":"4ea559bf2fdc7f3ed53589b973cf268f58641fb89ffc03fb1c83c432429e6641","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ea559bf2fdc7f3ed53589b973cf268f58641fb89ffc03fb1c83c432429e6641","first_computed_at":"2026-07-05T09:51:50.613533Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:51:50.613533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gTMLeeirKrolD3BmxCP09qsPLu+iZux5HSYLkwMmmAncIxmihx5s1lJP8DJUQpexuq5fyQxkwLhgtZP63/SuBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:51:50.614055Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.14637","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f6ccdb8172dab4bbcad862b038020a4f21fc5485eb17cfcb1ac29b337f84310","sha256:5d0432cecb3e0b0d110a153c9f16206ae244565911fa6e866f6fd0d07d3e0af1"],"state_sha256":"105b4deec4795680b4eb1ba722273cf8c809734100e23814aac6cc779dc02880"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6hnXgO+sbjd+uWpIXlD85sgx3MvAOrwMIbVt2p0SwUp39yG9X11m2cmE3liNdTWH6VSd7fZbWuk3edMnvqojAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T00:02:39.800950Z","bundle_sha256":"900731af6dd84b54b36bf0248698cdda1b2c0a3d5558142e018eccb77ccb06a2"}}